International Journal on Cybernetics & Informatics ( IJCI) Vol.2, No.4, August 2013 DOI: 10.5121/ijci.2013.2407 65 Adopting level set theory based algorithms to segment human ear Bijeesh T. V 1 and Nimmi I. P 2 Department of Computer Science and Engineering, Sree Narayana Guru College of Engineering and Technology, Payyanur, Kannur, Kerala, India 1 bijeeshtv@gmail.com, 2 nimmiip@gmail.com ABSTRACT Human identification has always been a topic that interested researchers around the world. Biometric methods are found to be more effective and much easier for the users than the traditional identification methods like keys, smart cards and passwords. Unlike with the traditional methods, with biometric methods the data acquisition is most of the times passive, which means the users do not take active part in data acquisition. Data acquisition can be performed using cameras, scanners or sensors. Human physiological biometrics such as face, eye and ear are good candidates for uniquely identifying an individual. However, human ear scores over face and eye because of certain advantages it has over face. The most challenging phase in human identification based on ear biometric is the segmentation of the ear image from the captured image which may contain many unwanted details. In this work, PDE based image processing techniques are used to segment out the ear image. Level Set Theory based image processing is employed to obtain the contour of the ear image. A few Level set algorithms are compared for their efficiency in segmenting test ear images. K EYWORDS Biometric identification, segmentation, PDE based image processing, Level set theory. 1. INTRODUCTION A Biometric is a measurable physical characteristic or a behavioral trait that can be used to authenticated a person. In this modern age of digital impersonation, authentication based on biometrics has become a more reliable measure against identity threats. The traditional authentication techniques such as keys and cards that the user has to carry with him always and the passwords and PINs the user has to remember always are fast becoming obsolete. Users find it difficult to carry the keys and cards or to remember the PINs. Moreover, forging keys, cards and PINs has now become the new trend among criminals. Thus an authentication mechanism based on biometric features is a necessity. Researchers across the world have widely studied physiological biometrics such as face and ear over the past few years. Both ear and face have been found to be an effective biometric to uniquely identify a human being. But biometric methods using ear holds an edge over face biometrics because of certain anatomical features of the ear. Ear is one of our sensory organs and is therefore usually not hidden or covered by anything so that hearing is not affected. This makes data acquisition process much easier and efficient. In case where face is used as the biometric, data acquisition may be difficult due to spectacles, beard or make-up. Also, ear is a very stable anatomical feature in the human body. The features of human ear do not change drastically with time. Besides, ear is unaffected by emotions. On the other hand facial features change significantly with age. Facial features are also affected by various emotions that a human being can go through.